jacooba / hyper
Code for the papers Hypernetworks in Meta-Reinforcement Learning (Beck et al., 2022) and Recurrent Hypernetworks are Surprisingly Strong in Meta-RL (Beck et al., 2023)
☆10Updated last month
Related projects: ⓘ
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆27Updated last week
- ☆25Updated this week
- An Open-Ended Agentic Simulator☆17Updated last month
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- ☆14Updated last month
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆22Updated last year
- Implementation (TensorFlow/keras) of the DreamerV3 model-based RL algorithm by Hafner et al. 2023☆3Updated last year
- ☆56Updated 3 weeks ago
- CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery☆77Updated 2 years ago
- Docker containers of baseline agents for the Crafter environment☆27Updated 2 years ago
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆13Updated last year
- Skeleton for scalable and flexible Jax RL implementations☆58Updated last year
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆49Updated 11 months ago
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆16Updated 8 months ago
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆26Updated last month
- ExORL: Exploratory Data for Offline Reinforcement Learning☆100Updated 2 years ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆51Updated 5 months ago
- Synthetic Experience Replay☆62Updated 3 months ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆76Updated last year
- Evaluating long-term memory of reinforcement learning algorithms☆129Updated last year
- Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELS☆20Updated 11 months ago
- General Modules for JAX☆57Updated last month
- ☆41Updated last year
- a simple and scalable agent for training adaptive policies with sequence-based RL☆79Updated this week
- Learning diverse options through the Laplacian representation.☆22Updated 8 months ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆71Updated 9 months ago
- Object Centric Atari games☆43Updated this week
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023☆42Updated 4 months ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆83Updated 7 months ago